Scene-text visual-style encoder (Chinese/English)
Chinese/English DINOv2 ViT-S/14 scene-text style encoder. It supports within-language and cross-language visual-style matching. The opaque repository name is not an access-control mechanism; this model is intentionally public.
Outputs
z_global [N,256]: overall typography and appearance.z_font [N,128]: font/typography-oriented representation.z_appearance [N,128]: fill, stroke, shadow, and opacity-oriented representation.style_tokens [N,8,384]: local research tokens; not validated as generator conditioning.
The three z_* tensors are L2-normalized. Supply a tightly cropped text instance or line.
Preprocessing preserves aspect ratio and pads to 112 x 448.
Install and use
git clone https://github.com/zqpresent/aaazhouquandecangku.git
cd aaazhouquandecangku
python -m pip install -e .
opaque-encoder download zqpresent/m7c1f9a2e4b8d6035a71 --local-dir weights
opaque-encoder encode --model weights --input crops --output styles.npz --device cpu --local-files-only
The complete fine-tuned backbone is included; no separate backbone download is required.
The loader checks the SHA-256 value in config.json.
Training scope and limitations
60,000 bilingual/replay groups / 1,920,000 rendered scene views. Font families, Chinese character partitions, and background sources used for final evaluation were held out from task training. Best suited to controlled synthetic Chinese/English text crops. Real photographs, other scripts, and generator conditioning are not validated. The encoder does not perform OCR. Synthetic retrieval evidence is not real-world accuracy, and low content/background probe scores do not prove zero leakage.
verification.json records source-to-export numerical parity. The source training checkpoint,
optimizer state, classifiers, data manifests, and local paths are not included in the inference weights.